Transputer Based Massively Parallel Architecture with Computation Intensive Applications 1

In this paper we present a massively parallel reconngurable system architecture, POPA (POstech PArallel computer) with computation intensive applications. It uses a reconng-urable interconnection network which can be dynamically controlled by software, providing the users with great exibility to choose the most eecient interconnection topology for their application. It consists of 64 processing elements with MIMD architecture to exploit various types of parallelism, and they are organized in distributed memory mode to maintain high performance/cost ratio. In order to support fast I/O, it provides a pool of input and output devices which can be directly attached to the processing elements through the interconnec-tion network. Also, the processing elements can be partitioned into multidomains of various size so that the system can be operated in a multiuser environment. Application softwares in a wide variety of computation intensive areas including optimization, neural network, cryptography , graphics, image processing, etc have been developed on various interconnection networks.